Image segmentation is a crucial task in computer vision, which divides a digital image into multiple segments and objects. In agriculture, image segmentation is extensively used for crop and soil monitoring, predicting the best times to sow, fertilize, and harvest, estimating crop yield, and detecting plant diseases. However, image segmentation faces difficulties in agriculture, such as the challenges of disease staging recognition, labeling inconsistency, and changes in plant morphology with the environment. Consequently, we have conducted a comprehensive review of image segmentation techniques based on deep learning, exploring the development and prospects of image segmentation in agriculture. Deep learning-based image segmentation solutions widely used in agriculture are categorized into eight main groups: encoder-decoder structures, multi-scale and pyramid-based methods, dilated convolutional networks, visual attention models, generative adversarial networks, graph neural networks, instance segmentation networks, and transformer-based models. In addition, the applications of image segmentation methods in agriculture are presented, such as plant disease detection, weed identification, crop growth monitoring, crop yield estimation, and counting. Furthermore, a collection of publicly available plant image segmentation datasets has been reviewed, and the evaluation and comparison of performance for image segmentation algorithms have been conducted on benchmark datasets. Finally, there is a discussion of the challenges and future prospects of image segmentation in agriculture.

Affected by global warming, the frequency of crop pests and diseases have increased, causing huge losses to agricultural production. To better grasp the development and trends of research on the effects of climate change on crop pests and diseases, the literature on the impact of climate change on crop pests and diseases published from 1990 to 2021 in the Web of Science (WOS) core collection database was used. This study explores the literature characteristics and hotspot evolution through the bibliometric visualization analysis software COOC, VOSviewer, and CiteSpace, with a view to identifying the changing characteristics and trends of research changes in this field. The results showed that the number of literature on the impact of climate change on crop pests and diseases increased rapidly. The main fields involved include environmental sciences, ecology, and agronomy. Papers in these fields mainly published in journals, such as PLos One, Forest Ecology and Management, and Frontiers in Plant Science. The country with the highest number of publications was the United States, followed by China and Australia. The most prolific authors in the top 20 are research scholars from China. The first author of the top 20 highly cited papers was from the United States. It was found that that current research on the impact of climate change on crop pests and diseases mainly focuses on agricultural production and food safety. Modelling and crop growth has maintained steady development. At present, research in this field mainly focuses on pest management strategies under the impact of climate change, the response of single species, and the complex ecological mechanisms behind the response. This study provides unique insights into the research field of the impact of climate change on crop pests and diseases and provides a reference direction for future research development in this field.

Excessive use of chemical fertilizers deteriorates the soil environment and limits the normal growth of Arabica coffee trees. In order to identify the optimal coupling mode of chemical fertilizer application and biomass return that enhances the soil ecological environment and promotes the photosynthetic efficiency of Arabica coffee, this study investigated the impacts of three levels of inorganic fertilizers (F_L: 360 kg·ha⁻¹, F_M: 720 kg·ha⁻¹, and F_H: 1080 kg·ha⁻¹) and three types of coffee husk returning methods (C_B: coffee husk biochar, C_C: coffee husk compost, C_A: coffee husk ash) on the soil fertility, microbial amount, enzyme activity, and photosynthetic characteristics of the Arabica coffee root zone. The entropy weight-TOPSIS method was employed to evaluate the comprehensive benefits. The results showed that F_M had the biggest effect on improving soil fertility, microorganisms, and enzyme activities compared with F_L and F_H. Moreover, compared to C_A, C_C significantly increased soil organic carbon, organic matter, and total nitrogen content. C_C significantly enhanced the activities of soil phosphatase and urease, respectively, by 29.84% and 96.00%, and significantly increased the amount of bacteria, fungi, and actinomycetes by 62.15%, 68.42%, and 46.21%, respectively. The net photosynthetic rate (Pn), transpiration rate (Tr), and stomatal conductance (Gs) of F_MC_C were significantly higher than those of other treatments. The comprehensive benefit evaluation of the soil environment and photosynthetic characteristics by the entropy weight-TOPSIS method ranked F_MC_C first. Therefore, F_MC_C was the optimal coupling mode for fertilizer application and the coffee husk returning method. The findings of this study not only provide scientific guidance for fertilizing Arabica coffee but also clarify the proper approach to returning coffee husk to the field, thereby improving soil ecology and promoting green and efficient production of specialty crops.

Rapeseed is one of China’s major oil crops, and accurate yield forecasting is crucial to the growth of the rapeseed industry and the country’s food security. In this study, the data on natural and socio-economic factors from 2001 to 2020 and the yield of rapeseed in China were used as the data basis. The Pearson correlation coefficient was used to analyze the relationship between the influencing factors and the yield of rapeseed, and the prediction effect of four machine learning models (linear regression (LR), decision tree (DTR), random forest (RF), and support vector machine (SVM)) on the yield of rapeseed was compared in China’s main rapeseed-producing area. The results demonstrate that the yield of rapeseed in China showed an increasing trend, but fluctuated greatly. Rural electricity consumption, gross agricultural production, the net amount of agricultural fertilizer application, effective irrigation area, total power of agricultural machinery, and consumption of agricultural plastic film had a positive effect on the increase in rapeseed yield. However, due to the impact of climate change and disasters, the yield of rapeseed has had significant fluctuations. A Pearson correlation analysis showed that socio-economic factors (rural electricity consumption, gross agricultural production, effective irrigation area, total power of agricultural machinery, consumption of agricultural plastic film, etc.) played a dominant role in rapeseed yield changes. The RF model had a good prediction effect on rapeseed yield, and natural factors and socio-economic factors had different effects on spring rapeseed and winter rapeseed. Winter rapeseed yield was mainly affected by socio-economic factors, accounting for as high as 89% of the importance. Among them, the sown area of rapeseed and the effective irrigation area had the greatest impact. The effects of natural factors and socio-economic factors on spring rapeseed yield were similar, accounting for 47% and 53%, respectively, and the mean annual precipitation, sunshine duration, and sown area of rapeseed were the most influential variables.

Unconventional water resources (e.g., saline water, etc.) for irrigation as a promising supplementary water source can alleviate the freshwater shortage in the agriculture of red soil areas in Southern China. It should be noted that the presence of soluble salt in this water source may have detrimental influences on soil water infiltration and crop growth. Understanding the effect of unconventional water irrigation (UWI) on water infiltration in red soil is important. Previous studies have shown that the salinity of UWI can alter soil hydraulic properties to change soil water movement in saline soils. However, the underlying mechanism and factors of water infiltration in red soil under UWI with different salinity levels remain limited. Therefore, a laboratory experiment (one-dimensional vertical infiltration experiment and centrifuge method) was conducted to evaluate the effect of UWI with different salinity levels [0 (the distilled water, CK), 1 (S1), 2 (S2), 3 (S3), 5 (S5), and 10 (S10) g L⁻¹] on the soil water infiltration process, soil water characteristic curve (SWCC), soil water constants estimated using the SWCC, saturated and unsaturated hydraulic conductivity (K_S and K) as well as the soil chemistry of soil profile [pH, electrical conductivity (EC), and Na⁺ and Cl⁻ contents]. The primary factors of soil water infiltration were identified using stepwise regression and path analysis methods. The results showed that UWI salinity decreased water infiltration by 1.53–7.99% at the end of infiltration in red soil, following the order of CK > S1 > S5 > S2 > S3 > S10. Moreover, UWI could enhance soil water availability with an increase of 8.55–12.68% in available water capacity. In contrast, lower K_S and K were observed in S1–S10, and there was a negative linear relationship between irrigation salinity and K_S. UWI also produced the EC, Na⁺, and Cl⁻ accumulations in the soil profile. As the salinity level of UWI increased, the accumulations aggravated. Soil acidification was found in S1–S5, while soil alkalization was observed in S10. Additionally, α, PWP, and K_S were the primary factors influencing the water infiltration of red soil. This study can help optimize the soil infiltration model under UWI and establish a foundation for unconventional water management in the red soil regions of Southern China and other similar regions. In addition, the undisturbed red soil under agricultural unconventional water irrigation and the long-term effect of unconventional water application should be considered.

Jatropha curcas L. is a promising bioenergy source, and its seedling stage is sensitive to salinity. Nitrogen application presents an effective strategy for alleviating the adverse consequences of salinity stress. However, the responses of plant growth and physiology of Jatropha curcas L. seedlings to nitrogen application under salinity stress remain unclear. As a result, a one-year greenhouse plot experiment was conducted to investigate the effects of nitrogen application on the plant growth, antioxidant enzyme activity, and photosynthesis of Jatropha curcas L. seedlings under saline conditions. Experiment treatments consisted of three salinity stresses (mild salinity stress, S1: 2 g/kg; moderate salinity stress, S2: 4 g/kg; and severe salinity stress, S3: 6 g/kg), four nitrogen application rates (N0: 0 gN/plant; N1: 20 gN/plant; N2: 60 gN/plant; and N3: 100 gN/plant), and a control treatment (CK) which was without salinity stress and nitrogen application. The results showed that salinity stress substantially reduced plant growth of Jatropha curcas L. seedlings. As the salinity stress increased, the reduction in plant growth also increased. The S3 treatment had the lowest leaf area, leaf biomass, and total biomass, which decreased by an average of 70.4%, 66.3%, and 69.9%, respectively, compared to CK. Nitrogen application could compensate for these impairments of plant growth from salinity stress by promoting antioxidant enzyme activity and photosynthesis. As for mild and moderate salinity stresses, the maximum plant growth was found in the N3 treatment, with the maximum antioxidant enzyme activity, photosynthetic pigment, photosynthetic characteristic, and chlorophyll fluorescence. As for severe salinity stress, higher plant growth was found in N2 and N3 treatments, and there were no significant differences between N2 and N3 treatments. It also should be noted that the maximum photosynthetic characteristic and chlorophyll fluorescence were found in N2 treatment under severe salinity stress. In conclusion, nitrogen application could be an alternative strategy to improve the salinity tolerance of Jatropha curcas L. growth. The nitrogen application rate of 100 gN/plant could be recommended for low and moderate salinity stresses, while 60 gN/plant could be recommended for severe salinity stress. However, higher nitrogen application rate (>100 gN/plant) under mild and moderate salinity stress and the effects of reactive oxygen species under salinity stress should be further evaluated.